← All roles

Software Engineer, RL Data

Apply on company site
Office location to be determinedPosted 1mo ago

About the role

SpaceXAI is building a Super Intelligence stack and the RL Data team focuses on creating training data and data pipelines to improve Grok models and related products. The role involves turning capability gaps into verifiable tasks, building production-like environments, designing graders for open-ended work, and creating automated checks to prevent data-quality issues as models train.

Responsibilities

  • Turning a capability gap into thousands of verifiable tasks — for example, planting subtle bugs deep in a real project's dependencies for the agent to root-cause.
  • Building environments that behave like production: real codebases with their real dependencies, and simulations of apps like email, calendar, and docs that match the real ones down to search, errors, and pagination.
  • Designing graders for open-ended work that separate good solutions from bad without penalizing valid alternatives or rewarding shortcuts.
  • Building automated checks that catch reward hacking, leaked answers, broken environments, and paths the real product wouldn't allow, before data reaches training.
  • Scaling from a thousand hand-checked tasks to millions, with filters and judges you can trust in place of a person reading each one

Qualifications

  • Strong software engineering fundamentals, and you've built non-trivial systems in Python: data pipelines, test or eval infrastructure, sandboxes, or backend services.
  • Taste for what makes an environment trustworthy: faithful enough that skills transfer, strict enough that shortcuts fail, and simple enough to debug when a result looks wrong.
  • Careful and systematic — understanding both aggregate metrics and close reading of raw outputs.
  • Enjoy turning messy, open-ended problems into repeatable, high-quality data production systems.
  • RL or ML experience is a plus but not required. We welcome strong engineers who want to do research on what makes models better.

Skills

Required:PythonSystems designExperimentation / A/B testingProduction-like environmentsReliability / data quality
Last updated Oct 15, 2026. Interested? Apply on the company site.
Cursor logo

About Cursor

The best way to code with AI

Built to make you extraordinarily productive, Cursor is the best way to build software with AI.

AIai-infrastructure-and-developmentai-plg-top-20brex-fastest-growing-2025code completionliquid-ai-recruiting-targetmultimodal agentsproductivity

More open roles at Cursor